IRJET- Classroom Attendance using Face Detection and Raspberry-Pi

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 05 Issue: 03 | Mar-2018

p-ISSN: 2395-0072

www.irjet.net

Classroom Attendance Using Face Detection and Raspberry-Pi Priya Pasumarti1, P. Purna Sekhar2 1Student,

Dept. of Electronics and Communication Engineering, Andhra Pradesh, India Professor, Dept. Electronics and Communication Engineering, Andhra Pradesh, India ---------------------------------------------------------------------***--------------------------------------------------------------------2Assistant

Abstract - Attendance for the students is an important

task in class. When done manually it generally wastes a lot of productive time of the class. This proposed solution for the current problem is through automation of attendance system using face recognition. Face is the primary identification for any human. This project describes the method of detecting and recognizing the face in real-time using Raspberry Pi. This project describes an efficient algorithm using open source image processing framework known as OpenCV. Our approach has five modules – Face Detection, Face Preprocessing, Face Training, Face Recognition and Attendance Database. The face database is collected to recognize the faces of the students. The system is initially trained with the student`s faces which is collectively known as student database. The system uses user friendly User interface to maximize the user experience while both training and testing which are collecting student images and taking attendance with the system. This project can be used for many other applications where face recognition can be used for authentication. Raspberry Pi usage helps in minimizing the cost of the product and the usability as it can be connected to any device to take the attendance. This project uses modified algorithm of Haar’s Cascades proposed by Viola-Jones for face detection and uses LBP histograms for face recognition and uses SQLite (lite version of SQL in raspberry pi) along with MYSQL to update the database. The system will automatically update the student’s presence in the class to the student’s database and sends message to guardians of absentees and also to Head of department.

face acknowledgment can be utilized for validation. In this proposed system we take the attendance using face recognition which recognizes the face of each student during the class hours.

2. BLOCK DIAGRAM

Fig -1: Block diagram of Proposed Approach

2.1 Raspberry Pi 3 The Raspberry Pi is a low cost, credit-card sized computer that plugs into a computer monitor or TV, and uses a standard keyboard and mouse. It is a capable little device that enables people of all ages to explore computing, and to learn how to program in languages like Scratch and Python.

This Raspberry pi equipped with ENC28J60 which is a Ethernet chip to get connected with internet [6].

Key Words: OpenCV, Raspberry Pi, Haar cascade, LBPH recognizer, Viola-Jones framework

1. INTRODUCTION The present day attendance system is manual. It wastes a considerable amount of time both for teachers and students. The waiting time of the students is increased if attendance is taken manually. There are still chances for proxies in the class when attendance is taken manually.

Manual attendance always a have a cost of human error.

Face is the essential recognizable proof for any human. So automating the attendance process will increase the productivity of the class. To make it available for every platform we have chosen the Raspberry pi 3 for face recognition. A Webcam is associated with the Raspberry Pi module. Face identification separates faces from non-faces and those countenances that can be perceived. This module can be utilized for different applications where © 2018, IRJET

|

Impact Factor value: 6.171

|

Fig -2: Raspberry Pi 3

2.2 Camera A camera is an optical instrument for recording or capturing images, which may be stored locally, transmitted to another location, or both. The images may be individual still photographs or sequences of images constituting videos or movies. The camera is a remote sensing device as it senses subjects without any contact.

ISO 9001:2008 Certified Journal

|

Page 167

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 05 Issue: 03 | Mar-2018

p-ISSN: 2395-0072

www.irjet.net

2.3 GPIO Pins General-purpose input/output (GPIO) is a generic pin on an integrated circuit or computer board whose behavior— including whether it is an input or output pin—is controllable by the user at run time.

Raspberry Pi’s console either by using SSH in laptop or by using Keyboard and mouse with the display device like TV connected to Pi. Firstly, the algorithm needs a lot of positive images and negative images to train the Haar cascades classifier. Positive images are images with clear faces where negative images are those without any faces.

2.4 Power Supply The Power Supply is a Primary requirement for the project work. The required DC power supply for the base unit as well as for the recharging unit is derived from the mains line. For this purpose center tapped secondary of 12V012V transformer is used. From this transformer we getting 5V power supply.

2.4 SD Card The OS required for raspberry pi is raspbian and the minimum recommended card size is 8 GB.

3. PROPOSED APPROACH The total system is divided into 3 modules- Database creation, Training the dataset, Testing, sending alert messages as an extension.

1. Database creation a) Initialize the camera and set an alert message to grab the attention of the students. b) Get user id as input c) convert the image into gray scale, detect the face and d) Store it in database by using given input as label up to 20 frames.

Fig -3: Haar Cascades Each feature is represented as a single value obtained from the difference of the sums of pixels in white rectangle from the sum of all pixels in the black rectangle. All different possible sizes and locations of classifier is used for calculating of plenty of features. As the number of classifiers increase the arithmetic computations seems to take a long time. To avoid this, we use the concept of Integral Image. In Image Processing Integral image is a data structure which is summed area table and algorithm for quickly and efficiently generating sum of values in a rectangular grid subset. Integral image is derived by using the formula.

2. Training a) Initialize LBPH face recognizer. b) Get faces and Id’s from database folder to train the LBPH face recognizer. c) Save the trained data as xml or yml file.

3. Testing Load Haar classifier, LBPH face recognizer and trained data from xml or yml file. a) Capture the image from camera, b) Convert it into gray scale, c) Detect the face in it and d) Predict the face using the above recognizer.

This proposed system uses Viola Jones algorithm [1] for face detection which uses modified Haar Cascades for detection.

Raspberry Pi is the main component in the project. We will be using USB webcam to capture photos. We can access © 2018, IRJET

|

Impact Factor value: 6.171

|

Fig -4: Integral image To solve the complexity of the number of classifiers applied for calculation we use Adaboost machine learning algorithm, which is inbuilt in OpenCV library that is cascade classifier, to eliminate the redundancy of the classifiers. Any classifier which has a probability of 50% of more in detection is treated as weak classifier. The Sum of all weak classifier gives a strong classifier which makes the decision about detection. Although it is very vague to classify with one strong classifier we use the cascade of classifiers. Classification takes place in stages, if the ISO 9001:2008 Certified Journal

|

Page 168

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 05 Issue: 03 | Mar-2018

p-ISSN: 2395-0072

www.irjet.net

selected region fails in the first stage, we discard it. We don’t use the classifiers on that region which is discarded.

The region which passes all the stages i.e. all strong classifiers is treated as the detected face. Detected Faces are passed to the Face recognition phase. In this phase we use Local Binary Patterns algorithm for face recognition.

Local binary patterns are simple at the same time very efficient texture operator which assigns the pixels of the image by comparing with the adjacent pixels as threshold and which results in a binary result. The detected integral image is subjected to this Local binary pattern which results in decimals are represented as histogram for every integral image. Face recognition is extremely vulnerable to the environment changes like brightness, facial expressions and position. Face preprocessing is the module which reduces the problems that makes the picture unclear to recognize the face such as less brightness and contrast problems and noise in the image and make sure the facial features always be in a constant position. In this project we use histogram equalization for face preprocessing. For efficiency we use separate preprocessing which is histogram equalization for left and right face. So histogram equalization is done three times, firstly for the whole face and the other two for side faces [7].

development in many areas on most platforms. The Python interpreter is easily extended with new functions and data types implemented in C or C++ (or other languages callable from C). Python is also suitable as an extension language for customizable applications.

4.2 OpenCV OpenCV is a library of programming functions mainly aimed at real-time computer vision. It has a modular structure, which means that the package includes several shared or static libraries. We are using image processing module that includes linear and non-linear image filtering, geometrical image transformations (resize, affine and perspective warping, and generic table-based remapping), color space conversion, histograms, and so on. Our project includes libraries such as Viola-Jones or Haar classifier, LBPH (Lower Binary Pattern histogram) face recognizer, Histogram of oriented gradients (HOG).

A) Image processing module Image processing is a method to perform some operations on an image, in order to get an enhanced image (simply to highlight certain features of interest in an image) or to extract some useful information from it. It is a type of signal processing in which input is an image and output may be image or characteristics/features associated with that image.

Purpose of Image processing The purpose of image processing is divided into 5 groups.

They are: 1. Visualization- Observe the objects that are not visible.

2. Image sharpening and restoration- To create a better image.

3. Image retrieval- Seek for the image of interest.

4. Measurement of pattern– Measures various objects in an image.

5. Image Recognition– Distinguish the objects in an image.

[5] i.

Fig -5: Flow Chart

4. ALGORITHMS 4.1 Python IDE Python is an easy to learn, powerful programming language. It has efficient high-level data structures and a simple but effective approach to object-oriented programming. Python’s elegant syntax and dynamic typing, together with its interpreted nature, make it an ideal language for scripting and rapid application © 2018, IRJET

|

Impact Factor value: 6.171

|

Haar Classifier

This object detection framework is to provide competitive object detection rates in real-time like detection of faces in an image. A human can do this easily, but a computer needs precise instructions and constraints. To make the task more manageable, Viola–Jones requires full view frontal upright faces. Thus in order to be detected, the entire face must point towards the camera and should not be tilted to either side. While it seems these constraints could diminish the algorithm's utility somewhat, because the detection step is most often followed by a recognition step, in practice these limits on pose are quite acceptable [2].

ISO 9001:2008 Certified Journal

|

Page 169

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 05 Issue: 03 | Mar-2018

p-ISSN: 2395-0072

www.irjet.net

The characteristics of Viola–Jones algorithm which make it a good detection algorithm are: a) Robust – very high detection rate (true-positive rate) & very low false-positive rate always. b) Real time – For practical applications at least 2 frames per second must be processed. c) Face detection only (not recognition) - The goal is to distinguish faces from non-faces (detection is the first step in the recognition process).

1. Divide the image into small connected regions called cells, and for each cell compute a histogram of gradient directions or edge orientations for the pixels within the cell.

2. Discretize each cell into angular bins according to the gradient orientation.

3. Each cell's pixel contributes weighted gradient to its corresponding angular bin.

4. Groups of adjacent cells are considered as spatial regions called blocks. The grouping of cells into a block is the basis for grouping and normalization of histograms.

5. Normalized group of histograms represents the block histogram. The set of these block histograms represents the descriptor [3].

B) Numpy NumPy is the fundamental package for scientific computing with Python. NumPy is an acronym for”Numeric Python” or “Numerical Python”. It is an open source extension module for Python, which provides fast precompiled functions for mathematical and numerical routines. Furthermore, NumPy enriches the programming language Python with powerful data structures for efficient computation of multi-dimensional arrays and matrices. The implementation is even aiming at huge matrices and arrays. Besides that the module supplies a large library of high-level mathematical functions to operate on these matrices and arrays.

Fig -6: Implementation This algorithm includes Haar feature selection process.

All human faces share some similar properties. These regularities may be matched using Haar Features.

A few properties common to human faces: a) b)

The eye region is darker than the uppercheeks.

The nose bridge region is brighter than the eyes.

Composition of properties forming matchable facial features: a) b)

Location and size: eyes, mouth, bridge of nose Value: oriented gradients of pixel intensities[4]

ii.

Histogram of oriented gradients (HOG)

Implementation of the HOG descriptor algorithm is as follows: |

Impact Factor value: 6.171

a) A powerful N-dimensional array object b) Sophisticated (broadcasting) functions c) Tools for integrating C/C++ and Fortran code d) Useful linear algebra, Fourier transforms, and random number capabilities.

Besides its obvious scientific uses, NumPy can also be used as an efficient multi-dimensional container of generic data.

Arbitrary data-types can be defined. This allows NumPy to seamlessly and speedily integrate with a wide variety of databases.

In our project we need to convert images into multidimensional or 2D-array representation, and also conversions from gray scale to color images which can be done easily by Numpy.

5. CONCLUSION

Histogram of oriented gradients (HOG) is a feature descriptor used to detect objects in computer vision and image processing. The HOG descriptor technique counts occurrences of gradient orientation in localized portions of an image - detection window, or region of interest (ROI).

© 2018, IRJET

It contains other things like:

|

We came to realize that there are extensive variety of methods, for example, biometric, RFID based and so on which are tedious and non-productive. So to defeat this above framework is the better and solid arrangement from each keen of time and security. Hence we have accomplished to build up a solid and productive participation framework to actualize an image handling algorithm to identify faces in classroom and to ISO 9001:2008 Certified Journal

|

Page 170

International Research Journal of Engineering and Technology (IRJET)

e-ISSN: 2395-0056

Volume: 05 Issue: 03 | Mar-2018

p-ISSN: 2395-0072

perceive the attendance.

confronts

precisely

to

www.irjet.net check

the

6. SCOPE and FUTURE WORK

[7] Soundrapandiyan Rajkumar, J. Prakash, “Automated attendance using Raspberry pi”, International Journal of Pharmacy and Technology, Sep 2016.

The same project can be utilized for several security applications where authentication is needed to access the privileges of the respective system. It can be used in recognizing guilty parties involving in unauthorized business. Face recognition algorithm can be improved with respect to the utilization of resources so that the project can recognize more number of faces at a time which can make the system far better. Many variants of the project can be developed and utilized for home security and personal or organizational benefits. We can also trace a particular student in an organization quickly with the help of this system.

ACKNOWLEDGEMENT Author would like to thank P. Purna Sekhar, Assistant Professor of Electronics and Communication Engineering for the technical support during system experimentation.

REFERENCES [1] Viola, P., & Jones, M. (2001). Rapid object detection using a boosted cascade of simple features. In Computer Vision and Pattern Recognition, 2001. CVPR 2001.

Proceedings of the 2001 IEEE Computer Society Conference on (Vol. 1, pp. I-511). IEEE. [2] Rohit, C., Baburao, P., Vinayak, F., &Sankalp, S. (2015). attendance management system using face recognition. International Journal for Innovative Research in Science and Technology, 1(11), 55-58.

[3] NirmalyaKar, MrinalKantiDebbarma, AshimSaha, and DwijenRudra Pal, “Implementation of Automated Attendance System using Face Recognition”, International Journal of Computer and Communication Engineering, Vol. 1, No. 2, July 2012.

[4]Benfano Soewito, Ford Lumban Gaol,” Attendance System on Android Smartphone”, 2015 International Conference on Control, Electronics, Renewable Energy and Communications (ICCEREC).

[5] AparnaBehara, M.V.Raghunadh, “Real Time Face Recognition System for time and attendance applications”, International Journal of Electrical, Electronic and Data Communication, ISSN 2320-2084, Volume-1, Issue-4.

[6] KAWAGUCHI, Y., SHOJI, T., Weijane, L. I. N., KAKUSHO, K., & MINOH, M. (2005). Face recognition-based lecture attendance system. In the 3rd AEARU Workshop on Network Education (pp. 70-75).

© 2018, IRJET

|

Impact Factor value: 6.171

|

ISO 9001:2008 Certified Journal

|

Page 171